Ettrickshepherd Mlx Dev Skill
- 6 repo stars
- Updated December 7, 2025
- ettrickshepherd/mlx-dev-skill
ettrickshepherd-mlx-dev-skill is a Claude Code plugin that guides agents to write idiomatic Apple MLX code on Apple Silicon.
About
ettrickshepherd-mlx-dev-skill is a one-skill Claude Code plugin that gives your agent a focused playbook for Apple’s MLX framework on M-series hardware. developers experimenting with on-device inference, fine-tuning small models, or shipping Apple Silicon–first utilities often get generic PyTorch or CUDA-oriented suggestions that do not compile or run well locally. This skill exists to bias completions toward MLX idioms—memory layout, device placement, and framework conventions—so you spend less time unwinding hallucinated APIs. It is best treated as a accelerator when you already committed to MLX rather than a vendor-neutral model router. You still need Xcode command-line tools, a working Python environment, and realistic expectations about model size on laptop RAM. After install, prompts about training loops, MLX modules, and Silicon-specific optimizations should produce more copy-pasteable code. It does not replace MLX documentation or Apple’s release notes when APIs change.
- Single Claude Code skill focused on idiomatic Apple MLX APIs on Apple Silicon
- Steers agents away from PyTorch-on-Mac mistakes toward MLX-native patterns
- Targets local LLM and ML experimentation without cloud GPU dependency
- Lightweight plugin (1 skill) from ettrickshepherd/mlx-dev-skill repository
- Pairs with agent-driven iteration on MLX arrays, models, and Apple Silicon performance
Ettrickshepherd Mlx Dev Skill by the numbers
- Data as of Jul 7, 2026 (Skillselion catalog sync)
/plugin install ettrickshepherd-mlx-dev-skill@ettrickshepherd/mlx-dev-skillAdd your badge
Show developers this plugin is listed on Skillselion. Paste this into your README.
| repo stars | ★ 6 |
|---|---|
| Last updated | December 7, 2025 |
| Repository | ettrickshepherd/mlx-dev-skill ↗ |
What it does
Teach your coding agent to write correct, idiomatic Apple MLX Python on M-series Macs for local model inference and training experiments.
Who is it for?
Best when you're shipping MLX-based prototypes, local LLM tools, or Mac-native ML utilities and want agent output aligned with Apple’s stack.
Skip if: Cloud-only GPU pipelines, non-Apple hardware, or teams standardized on PyTorch/JAX without MLX.
What you get
Your Claude Code sessions produce MLX-native Python that fits local inference and training on your Mac.
- MLX-aligned Python modules, training snippets, and inference scripts
- Agent answers that reference Silicon-appropriate patterns instead of CUDA defaults
By the numbers
- Plugin count: 1 skill
- Repository: ettrickshepherd/mlx-dev-skill
- Catalog GitHub stars: 6
Recommended Plugins
Abix5 Memory HindsightHindsight memory bank integration for Claude Code
Agentic Dev Io Mcp Code ExecutionToken-efficient MCP server interaction through code execution.1
Agneym Agneym Claude MarketplaceClaude Code plugin marketplace for Agney's plugins
Akkomar Mozdata Claude Plugin1 plugin
Amitpatole Claude Genkit PluginFirebase Genkit Plugin for Claude Code12
Aserper RtfdSpoonfeed your AI coding assistant with up to date documentation efficiently and without using a cloud service with the RTFD mcp server that runs on YOUR machine without any API key requirements!14How it compares
Framework-specific agent skill, not an MLX MCP server or hosted inference API.
FAQ
Who is Ettrickshepherd Mlx Dev Skill for?
It is for developers on Apple Silicon who use Claude Code to write MLX Python and want fewer incorrect cross-framework suggestions.
When should I use Ettrickshepherd Mlx Dev Skill?
Use it during implementation whenever you are adding MLX models, training scripts, or inference utilities on a Mac.
How do I add Ettrickshepherd Mlx Dev Skill to my agent?
Add the ettrickshepherd/mlx-dev-skill repository as a Claude Code plugin, enable the single bundled skill, and ensure your project has MLX and Python dependencies installed locally.